A Conditional Generative Matching Model for Multi-lingual Reply Suggestion
arXiv:2109.07046
Abstract
We study the problem of multilingual automated reply suggestions (RS) model serving many languages simultaneously. Multilingual models are often challenged by model capacity and severe data distribution skew across languages. While prior works largely focus on monolingual models, we propose Conditional Generative Matching models (CGM), optimized within a Variational Autoencoder framework to address challenges arising from multi-lingual RS. CGM does so with expressive message conditional priors, mixture densities to enhance multi-lingual data representation, latent alignment for language discrimination, and effective variational optimization techniques for training multi-lingual RS. The enhancements result in performance that exceed competitive baselines in relevance (ROUGE score) by more than 10\% on average, and 16\% for low resource languages. CGM also shows remarkable improvements in diversity (80\%) illustrating its expressiveness in representation of multi-lingual data.
References in corpus (8)
- Cross-lingual Language Model Pretraining
- Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
- Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models
- Continual Unsupervised Representation Learning
- Training Neural Response Selection for Task-Oriented Dialogue Systems
- What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning
- Diversifying Reply Suggestions using a Matching-Conditional Variational Autoencoder
- Modelling Latent Skills for Multitask Language Generation